Security audit
Security checks across malware telemetry and agentic risk
This appears to be a real pharma research skill, but it needs review because its helper scripts can make broadly scoped web requests and save fetched data to caller-chosen local file paths.
Install only if you are comfortable with a research skill that can run Python scripts making outbound HTTP requests and optionally writing raw API responses to local files. Prefer running it in a sandboxed environment, avoid passing untrusted JSON directly to the scripts, do not use save_raw or raw_output_path unless necessary, and review generated commands before execution.
raw_text = json.dumps(data, indent=2)
path = Path(config["raw_output_path"] or "/tmp/gnomad-graphql.json")
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(raw_text, encoding="utf-8")
raw_output_path = str(path)
if "errors" in data:)
path = Path(config["raw_output_path"] or "/tmp/opentargets-associated-diseases.json")
path.parent.mkdir(parents=True, exist_ok=True)
path.write_text(raw_text, encoding="utf-8")
raw_output_path = str(path)
if disease_filter and not filtered_rows:65/65 vendors flagged this skill as clean.
No suspicious patterns detected.